Amazon Orders

io.github.alexdlaird由 GitHub 帳號 alexdlaird 發布v1.2.0更新於 Oct 24, 2026

An MCP server for Amazon order history, line items, and transactions, built on amazon-orders

已驗證STDIO僅桌面金融商業與電商

概覽

AI 產生的概覽

非官方本機 MCP 伺服器,讓助理讀取你的 Amazon 訂單紀錄、訂單明細、物流、發票與交易資料。

可以做什麼
  • 登入 Amazon 各站點並檢查目前哪些站點已登入
  • 依年份、時間範圍、訂單類型、商品、訂單編號、地址或收件人列出、搜尋並取得訂單
  • 取得貨件承運商與追蹤編號,以及訂單可列印摘要和賣家發票 PDF
  • 讀取付款交易、禮品卡餘額與異動,以及 Prime 會員費用扣款
  • 讀取並變更伺服器本身的設定,例如預設 Amazon 站點
適用情境
適合想請助理回答自己 Amazon 購物相關問題時使用,例如近期訂單、貨件進度、某筆訂單花費、禮品卡餘額或 Prime 費用,並可涵蓋你常用的多個 Amazon 站點,不必手動匯出資料。
執行需求
透過 uvx(或 pip)在本機以 stdio 程序執行;需要 Python 工具鏈,瀏覽器登入需要桌面環境,無顯示器的機器須先在終端機登入。可選的 Streamable HTTP 模式預設只監聽本機回環位址。未宣告 API 金鑰或環境變數;登入在 Amazon 自家頁面完成並沿用工作階段。
安裝前請注意
它透過 Amazon 面向消費者的網站讀取帳戶資料,而非官方 API,Amazon 改版時可能失效。登入憑證在 Amazon 頁面輸入,但伺服器會沿用留下的工作階段,並與 amazon-orders 命令列工具共用。工具可變更設定;若把 HTTP 傳輸開放至回環位址以外,必須啟用 bearer token。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Amazon Orders,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README

[amazon-orders-mcp - An MCP server for Amazon order history]

[Version] [Python Versions] [Build] [GitHub License]

amazon-orders-mcp is an unofficial MCP server for Amazon order history, line items, and transactions, built on amazon-orders. It gives your AI assistant tools for your Amazon account, available from any MCP client.

The server never sees your credentials. When you sign in, a browser window opens on Amazon's own page, and the server reuses the session that leaves behind. It also runs on a server without a display, where you sign in from a terminal instead (see Remote Clients).

Note: This server reads its data through amazon-orders, which works by parsing data from Amazon's consumer-facing website. As Amazon provides no official API to use, older versions may break at any time, so it's recommended that you use the latest version.

Installation

amazon-orders-mcp is available on PyPI and is run with uvx, so there's nothing to install up front. Add it to your AI assistant:

ChatGPT

ChatGPT Desktop: in Settings → Plugins, add an MCP server of type STDIO, with uvx as the command and amazon-orders-mcp as its argument.

Codex:

sh
codex mcp add amazon-orders -- uvx amazon-orders-mcp

Claude

Claude Desktop: download amazon-orders-mcp-<version>.mcpb from the latest release and open it.

Claude Code:

sh
claude mcp add amazon-orders -- uvx amazon-orders-mcp

Other Clients

Any client that runs local MCP servers can use this JSON, or amazon-orders-mcp as the command if you've installed it with pip install amazon-orders-mcp:

json
{  "mcpServers": {    "amazon-orders": {      "command": "uvx",      "args": ["amazon-orders-mcp"]    }  }}

Remote Clients

For clients that connect to a server instead of running one, the server can also serve Streamable HTTP:

sh
uvx amazon-orders-mcp --transport streamable-http

It listens at http://127.0.0.1:8000/mcp. See --help to change that, or to require a bearer token (required off loopback). On a server without a display, sign_in can't open a browser window, so sign in there first with uvx amazon-orders login, which asks for your username and password instead.

Docker

sh
docker build -t amazon-orders-mcp .docker run -i --rm -v amazon-orders:/home/app/.config/amazonorders amazon-orders-mcp

A container has no display, so sign in with the login target first. See the Dockerfile for how.

Basic Usage

Just ask your assistant about your orders, and it will use the following tools:

ToolReturns
sign_inOpens a browser window for you to sign in to Amazon, when you ask
get_ordersA batch of orders by year, time filter or order type, optionally detailed
search_ordersA batch of items by product, order number, address or recipient, any year
get_orderOne order, by order number
get_trackingA shipment's carrier and tracking number, from an order's shipment ID
get_invoicesAn order's printable summary, and any invoice PDFs the seller issues
get_transactionsA batch of payment transactions over a number of days, or for an order
get_gift_cardsThe Gift Card balance, with a batch of its activity over a number of days
get_prime_paymentsPrime membership fee charges, each with its order number
check_sessionWhether you're signed in, on each Amazon site you have a session for
get_configThe settings your assistant can change, and their values
update_configChanges one of those settings

Order history and transactions come back in batches of limit results (25 by default, and a batch can run up to a page over), with a cursor your assistant passes back to get the next batch.

Every tool that reads Amazon takes an optional site, like amazon.de, so your assistant can read each Amazon site you shop on from one server, e.g. "my last amazon.de orders". Without it, tools read your default site, the domain setting. Each site has its own sign-in, so ask your assistant to sign you in to each one.

Configuration

Ask your assistant to change a setting, such as the default Amazon site (e.g. amazon.co.uk) or the browser to sign in with. Settings are shared with the amazon-orders CLI, so it follows the same changes. See Supported Sites for the sites amazon-orders can read.

Documentation

For more on the data the server returns, amazon-orders's official documentation is available at Read the Docs, including the Order entity's fields and troubleshooting.

Contributing

Want to contribute financially? If you've found amazon-orders-mcp useful, sponsorship would be greatly appreciated!

來源:README.md,提交 4fd6fa6

工具

0
SourceWeft 尚未在沙箱中啟動過該軟體包,因此其工具未知。

版本歷史

1
  1. v1.2.0最新Oct 15, 2026

評分

已滿足適用檢查項的 50%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通25 分

    請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。

  • 已宣告認證方式10 分

    請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。

  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分